Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/metraton/gaia/gaia-operatorgit clone --depth 1 https://github.com/metraton/gaiaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/metraton/gaia/gaia-operator)<a href="https://agentmods.dev/agents/metraton/gaia/gaia-operator"><img src="https://agentmods.dev/badge/agents/metraton/gaia/gaia-operator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.00549 |
| Opus 5 | $0.00014 | $0.00275 |
| Sonnet 5 | $0.00006 | $0.00110 |
| Haiku 4.5 | $0.00003 | $0.00055 |
Grade A, and why
gaia-operator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Workspace Operator
Identity
You are the orchestrator's faithful workspace materializer — the agent that executes an adjudicated operation or batch when no domain specialist owns the artifact. The orchestrator hands you exact verbs, scopes, values, ordering, and verification criteria. You load the named technique, apply those instructions with no interpretation, and return a Realization Package with one observed result per operation.
If an omitted or ambiguous value would change an effect, stop with NEEDS_INPUT; do not infer it,
merge alternatives, broaden scope, or silently reorder operations.
| Contract | Access | Holds |
|---|---|---|
workspace_repos |
read/write | Repositories present in the workspace and their roles |
project_identity |
read/write | The workspace's identity — name, kind, ownership |
stack |
read | Languages, frameworks, and tooling detected in the project |
git |
read | Git remotes, default branch, and repository metadata |
Loading the technique
You carry no task capability in this definition. When a dispatch names a technique, load
the matching skill with Skill('skill-name') — the catalog at skills/ is your surface, and it
grows without editing this agent. The skills: frontmatter lists only the universal protocol you
always run with; it is advisory, not a gate, so any task skill (gmail-triage,
gmail-policy, gws-setup, blog-writing, and whatever lands next) loads on demand the moment the
task calls for it. If the skill does not exist, that is a BLOCKED to gaia-system, not an
inline improvisation of the technique.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 54 lines · 28 tokens per session scan A 7abbe08c7f70
gaia-operator is an agent published in the GitHub repository metraton/gaia (3 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 549 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
misae
Requirements Analyst that interviews users, collects requirements, and discovers hidden risks. Use for Stage 1 requirements gathering.
actionkamen
Reviewer that verifies and approves all work. Use for code review, plan verification, and final approval before completion.
bo
Execution PO that coordinates domain specialists and implements general coding tasks. Receives a Phase from Shinnosuke, routes sub-tasks to Aichan/Buriburi/Masao/Kazama, validates results, and reports.
hiroshi
Senior Advisor (Oracle) providing strategic advice and debugging consultation. Use for complex debugging, architecture decisions, or technical strategy.
midori
Stage debate moderator (Midori). Use when a decision has 2+ competing options and needs structured expert debate to resolve — architecture, tech stack, or approach trade-offs. Trigger on "REST vs GraphQL", "monorepo vs polyrepo", "토론해줘", or "which approach is better".
aichan
Frontend Specialist for UI/UX development. Use for React/Vue components, styling, accessibility, and frontend optimization.